Re: [Math] FastMath Performance

2011-01-26 Thread Gilles Sadowski
Hi. > FastMath aims to give the best accuracy possible given the > constraint of IEEE binary double precision representation, while > also giving superior performance. This what I meant by: > >I'd say (and the name "FastMath" reflects that) that it is a fast > >replacement of "Math". Thus all "M

Re: [Math] FastMath Performance

2011-01-26 Thread Bill Rossi
On Wed, 26 Jan 2011, Gilles Sadowski wrote: On Wed, Jan 26, 2011 at 12:12:47PM +, sebb wrote: On 26 January 2011 11:05, Gilles Sadowski wrote: Hi. I'd wish to make it clear that I referred to this statement: The Javadoc for FastMath says that it is a replacement for StrictMath, whi

Re: [Math] FastMath Performance

2011-01-26 Thread Gilles Sadowski
On Wed, Jan 26, 2011 at 12:12:47PM +, sebb wrote: > On 26 January 2011 11:05, Gilles Sadowski > wrote: > > Hi. > > > > I'd wish to make it clear that I referred to this statement: > > > >> > > The Javadoc for FastMath says that it is a replacement for > >> > StrictMath, > >> > > which is why

Re: [Math] FastMath Performance

2011-01-26 Thread sebb
On 26 January 2011 11:05, Gilles Sadowski wrote: > Hi. > > I'd wish to make it clear that I referred to this statement: > >> > > The Javadoc for FastMath says that it is a replacement for >> > StrictMath, >> > > which is why I tested against that. > > An my understanding was: > >> > Unless I'm mis

Re: [Math] FastMath Performance

2011-01-26 Thread Gilles Sadowski
Hi. I'd wish to make it clear that I referred to this statement: > > > The Javadoc for FastMath says that it is a replacement for > > StrictMath, > > > which is why I tested against that. An my understanding was: > > Unless I'm missing something, this is a doc mistake then. So we have: [Pleas

Re: [Math] FastMath Performance

2011-01-25 Thread Bill Rossi
On Tue, 25 Jan 2011, luc.maison...@free.fr wrote: Hi Gilles, - "Gilles Sadowski" a écrit : Hello. [...] Note: this appears to be at least as quick as StrictMath on Sun Java 1.6 in a crude test The performance comparison for "FastMath" should be against "Math", as "StrictMath is

Re: [Math] FastMath Performance

2011-01-25 Thread luc . maisonobe
Hi Gilles, - "Gilles Sadowski" a écrit : > Hello. > > > > [...] > > >> Note: this appears to be at least as quick as StrictMath on Sun > Java 1.6 in a crude test > > > > > > The performance comparison for "FastMath" should be against > "Math", as "StrictMath > > > is expected to be slow(er)

Re: [Math] FastMath Performance

2011-01-25 Thread Gilles Sadowski
Hello. > > [...] > >> Note: this appears to be at least as quick as StrictMath on Sun Java 1.6 > >> in a crude test > > > > The performance comparison for "FastMath" should be against "Math", as > > "StrictMath > > is expected to be slow(er). [That's why I've added the calls to "Math" in > > th

Re: [Math] FastMath Performance (Was: [jira] Resolved: (MATH-493) ...)

2011-01-24 Thread sebb
On 24 January 2011 13:11, Gilles Sadowski wrote: > Hi. > >> Sebb resolved MATH-493. >> --- >> >>     Resolution: Fixed >> >> Fixed by using the Harmony code. >> >> Note: this appears to be at least as quick as StrictMath on Sun Java 1.6 in >> a crude test > > The performance c

[Math] FastMath Performance (Was: [jira] Resolved: (MATH-493) ...)

2011-01-24 Thread Gilles Sadowski
Hi. > Sebb resolved MATH-493. > --- > > Resolution: Fixed > > Fixed by using the Harmony code. > > Note: this appears to be at least as quick as StrictMath on Sun Java 1.6 in a > crude test The performance comparison for "FastMath" should be against "Math", as "Strict